Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I actually think this is a fairly trainable attribute. Given that Tesla does this kind of detection for objects and classification and records many miles of human drivers - it wouldn't be surprising that this may be a learned trait.


It's the corner cases... like Halloween, or body posture, or crossing behind a semi-transparent asymmetric object.


Fair point. This is far less likely.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: